An Optical-flow based Segmentation Algorithm for Gait Recognition

The quality of human silhouettes has a direct effect on gait recognition performance. This paper proposes a robust gait representation scheme to suppress the influence of silhouette incompleteness. By means of dividing the human body into regions in a video sequence of several sub-regions, representing each sub-region through an ellipse whose parameters can be calculated from the corresponding motion information extracted from optical flow field, by which a new body structure model called multi-linked ellipse model is established. In the recognition stage, the parameters of the model are finally used to achieve gait recognition based on dynamic time warping technology. Experimental results prove the higher performance of our method.